Low speed performence improvement of sensorless IM control system based on MRAS and NN flux observers

Many electronic drivers for the induction motor control are based on sensorless technologies. This paper proposes a novel hybrid motion sensorless control system to solve the low speed problems using MRAS and NN estimation scheme which is based on rotor flux. A multilayer feedforward artificial neural network is proposed for rotor flux estimation which is more robust to noise and stator resistance variation and does not have de-drift problems which are usually associated with these adaptive schemes. A comparison between the performance of the neural network based strategy and conventional scheme is carried out. Simulation results are also presented to validate the proposed approach.